© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-RES-262K
    4. 3760
    Prev
    Next
    INDEX
    Explanations

    original academic technical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     screenings
    0.35
     screening
    0.34
    っと
    0.34
    кей
    0.31
     sustainably
    0.31
    leur
    0.31
    屏
    0.31
     enhancement
    0.30
    ាត់
    0.30
    йте
    0.30
    POSITIVE LOGITS
    论文
    0.39
     Compress
    0.39
    代码
    0.36
     ब
    0.34
    Compress
    0.34
     compress
    0.33
    Algorithm
    0.33
     代码
    0.33
     b
    0.32
     compres
    0.32
    Activations Density 0.000%

    No Known Activations